Hengkai Tan

Songming Liu, Bangguo Li, Kai Ma et al.

Vision-Language-Action (VLA) models hold promise for generalist robotics but currently struggle with data scarcity, architectural inefficiencies, and the inability to generalize across different hardware platforms. We introduce RDT2, a robotic foundation model built upon a 7B parameter VLM designed to enable zero-shot deployment on novel embodiments for open-vocabulary tasks. To achieve this, we collected one of the largest open-source robotic datasets--over 10,000 hours of demonstrations in diverse families--using an enhanced, embodiment-agnostic Universal Manipulation Interface (UMI). Our approach employs a novel three-stage training recipe that aligns discrete linguistic knowledge with continuous control via Residual Vector Quantization (RVQ), flow-matching, and distillation for real-time inference. Consequently, RDT2 becomes one of the first models that simultaneously zero-shot generalizes to unseen objects, scenes, instructions, and even robotic platforms. Besides, it outperforms state-of-the-art baselines in dexterous, long-horizon, and dynamic downstream tasks like playing table tennis. See https://rdt-robotics.github.io/rdt2/ for more information.

Yao Feng, Chendong Xiang, Xinyi Mao et al.

Robotic arm manipulation in data-scarce settings is a highly challenging task due to the complex embodiment dynamics and diverse contexts. Recent video-based approaches have shown great promise in capturing and transferring the temporal and physical interactions by pre-training on Internet-scale video data. However, such methods are often not optimized for the embodiment-specific closed-loop control, typically suffering from high latency and insufficient grounding. In this paper, we present Vidarc (Video Diffusion for Action Reasoning and Closed-loop Control), a novel autoregressive embodied video diffusion approach augmented by a masked inverse dynamics model. By grounding video predictions with action-relevant masks and incorporating real-time feedback through cached autoregressive generation, Vidarc achieves fast, accurate closed-loop control. Pre-trained on one million cross-embodiment episodes, Vidarc surpasses state-of-the-art baselines, achieving at least a 15% higher success rate in real-world deployment and a 91% reduction in latency. We also highlight its robust generalization and error correction capabilities across previously unseen robotic platforms.

MotuBrain Team, Chendong Xiang, Fan Bao et al.

Vision-Language-Action (VLA) models achieve strong semantic generalization but often lack fine-grained modeling of world dynamics. Recent work explores video generation models as a foundation for world modeling, leading to unified World Action Models (WAMs) that jointly model visual dynamics and actions. We present MotuBrain, a unified multimodal generative model that jointly models video and action under a UniDiffuser formulation with a three-stream Mixture-of-Transformers architecture. A single model supports multiple inference modes, including policy learning, world modeling, video generation, inverse dynamics, and joint video-action prediction, while scaling to heterogeneous multimodal data such as video-only and cross-embodiment robot data. To improve real-world applicability, MotuBrain introduces a unified multiview representation, explicit language-action coupling, and an efficient inference stack, achieving over 50x speedup for real-time deployment.

Hengkai Tan, Xuezhou Xu, Chengyang Ying et al. · tsinghua

Learning a precise robotic grasping policy is crucial for embodied agents operating in complex real-world manipulation tasks. Despite significant advancements, most models still struggle with accurate spatial positioning of objects to be grasped. We first show that this spatial generalization challenge stems primarily from the extensive data requirements for adequate spatial understanding. However, collecting such data with real robots is prohibitively expensive, and relying on simulation data often leads to visual generalization gaps upon deployment. To overcome these challenges, we then focus on state-based policy generalization and present \textbf{ManiBox}, a novel bounding-box-guided manipulation method built on a simulation-based teacher-student framework. The teacher policy efficiently generates scalable simulation data using bounding boxes, which are proven to uniquely determine the objects' spatial positions. The student policy then utilizes these low-dimensional spatial states to enable zero-shot transfer to real robots. Through comprehensive evaluations in simulated and real-world environments, ManiBox demonstrates a marked improvement in spatial grasping generalization and adaptability to diverse objects and backgrounds. Further, our empirical study into scaling laws for policy performance indicates that spatial volume generalization scales with data volume in a power law. For a certain level of spatial volume, the success rate of grasping empirically follows Michaelis-Menten kinetics relative to data volume, showing a saturation effect as data increases. Our videos and code are available in https://thkkk.github.io/manibox.

Hongzhe Bi, Lingxuan Wu, Tianwei Lin et al.

Imitation learning for robotic manipulation faces a fundamental challenge: the scarcity of large-scale, high-quality robot demonstration data. Recent robotic foundation models often pre-train on cross-embodiment robot datasets to increase data scale, while they face significant limitations as the diverse morphologies and action spaces across different robot embodiments make unified training challenging. In this paper, we present H-RDT (Human to Robotics Diffusion Transformer), a novel approach that leverages human manipulation data to enhance robot manipulation capabilities. Our key insight is that large-scale egocentric human manipulation videos with paired 3D hand pose annotations provide rich behavioral priors that capture natural manipulation strategies and can benefit robotic policy learning. We introduce a two-stage training paradigm: (1) pre-training on large-scale egocentric human manipulation data, and (2) cross-embodiment fine-tuning on robot-specific data with modular action encoders and decoders. Built on a diffusion transformer architecture with 2B parameters, H-RDT uses flow matching to model complex action distributions. Extensive evaluations encompassing both simulation and real-world experiments, single-task and multitask scenarios, as well as few-shot learning and robustness assessments, demonstrate that H-RDT outperforms training from scratch and existing state-of-the-art methods, including Pi0 and RDT, achieving significant improvements of 13.9% and 40.5% over training from scratch in simulation and real-world experiments, respectively. The results validate our core hypothesis that human manipulation data can serve as a powerful foundation for learning bimanual robotic manipulation policies.

Hongzhe Bi, Hengkai Tan, Shenghao Xie et al.

While a general embodied agent must function as a unified system, current methods are built on isolated models for understanding, world modeling, and control. This fragmentation prevents unifying multimodal generative capabilities and hinders learning from large-scale, heterogeneous data. In this paper, we propose Motus, a unified latent action world model that leverages existing general pretrained models and rich, sharable motion information. Motus introduces a Mixture-of-Transformer (MoT) architecture to integrate three experts (i.e., understanding, video generation, and action) and adopts a UniDiffuser-style scheduler to enable flexible switching between different modeling modes (i.e., world models, vision-language-action models, inverse dynamics models, video generation models, and video-action joint prediction models). Motus further leverages the optical flow to learn latent actions and adopts a recipe with three-phase training pipeline and six-layer data pyramid, thereby extracting pixel-level "delta action" and enabling large-scale action pretraining. Experiments show that Motus achieves superior performance against state-of-the-art methods in both simulation (a +15% improvement over X-VLA and a +45% improvement over Pi0.5) and real-world scenarios(improved by +11~48%), demonstrating unified modeling of all functionalities and priors significantly benefits downstream robotic tasks.

Yao Feng, Hengkai Tan, Xinyi Mao et al.

Scaling general-purpose manipulation to new robot embodiments remains challenging: each platform typically needs large, homogeneous demonstrations, and pixel-to-action VLA pipelines typically degenerate under background and viewpoint shifts. In this paper, we present Vidar, a prior-driven, low-shot adaptation paradigm that replaces most embodiment-specific data with transferable video priors. Vidar consists of an embodied video diffusion model as the generalizable prior and a masked inverse dynamics model (MIDM) adapter based on a key decoupling of the policy. The embodied diffusion model is pre-trained on Internet-scale videos and then domain-adapted to 750K multi-view trajectories from three real-world robot platforms using a unified observation space encoding robot, camera, task, and scene contexts. The MIDM module learns action-relevant pixel masks without dense labels, grounding the prior into the target embodiment's action space while suppressing distractors. Crucially, the generative video prior models the distribution of plausible, temporally coherent interactions, implicitly capturing affordances, contact dynamics, and physical consistency from massive unlabeled video. This shifts the challenge from collecting large amounts of new robot data to efficiently aligning a rich prior with a new embodiment. With only 20 minutes of human demonstrations on an unseen robot (1% of typical data), Vidar outperforms state-of-the-art VLA baselines and generalizes to unseen tasks, backgrounds, and camera layouts. Our results suggest a scalable recipe for "one prior, many embodiments": strong, inexpensive video priors + minimal on-robot alignment.

Hengkai Tan, Yao Feng, Xinyi Mao et al.

Vision-language-action (VLA) models have shown promise on task-conditioned control in complex settings such as bimanual manipulation. However, the heavy reliance on task-specific human demonstrations limits their generalization and incurs high data acquisition costs. In this work, we present a new notion of task-agnostic action paradigm that decouples action execution from task-specific conditioning, enhancing scalability, efficiency, and cost-effectiveness. To address the data collection challenges posed by this paradigm -- such as low coverage density, behavioral redundancy, and safety risks -- we introduce ATARA (Automated Task-Agnostic Random Actions), a scalable self-supervised framework that accelerates collection by over $ 30\times $ compared to human teleoperation. To further enable effective learning from task-agnostic data, which often suffers from distribution mismatch and irrelevant trajectories, we propose AnyPos, an inverse dynamics model equipped with Arm-Decoupled Estimation and a Direction-Aware Decoder (DAD). We additionally integrate a video-conditioned action validation module to verify the feasibility of learned policies across diverse manipulation tasks. Extensive experiments show that the AnyPos-ATARA pipeline yields a 51% improvement in test accuracy and achieves 30-40% higher success rates in downstream tasks such as lifting, pick-and-place, and clicking, using replay-based video validation. Project Page: https://embodiedfoundation.github.io/vidar_anypos